INDEX

Explanations

details and specific attributes related to biological or technical classifications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IsMutable

-0.65

 ब्रेकडाउन

-0.65

WebServlet

-0.52

DockStyle

-0.52

 HasFactory

-0.52

__":

-0.52

__':

-0.51

Datuak

-0.50

__":

-0.50

IsContent

-0.50

POSITIVE LOGITS

delwed

0.49

就知道

0.37

السكان

0.36

Cay

0.35

unmodifiable

0.34

MOS

0.32

ルメ

0.31

 poveznice

0.31

mately

0.30

Snoo

0.30

Activations Density 0.226%

details and specific attributes related to biological or technical classifications

No Comments

No Known Activations